{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/a2-rl-aesthetics-aware-reinforcement-learning","title":"A2-RL: Aesthetics Aware Reinforcement Learning for Image Cropping","arxiv_id":"1709.04595","date":"2017-09-14","proceeding":"CVPR 2018 6","authors":["Debang Li","Huikai Wu","Junge Zhang","Kaiqi Huang"],"abstract":"Image cropping aims at improving the aesthetic quality of images by adjusting\ntheir composition. Most weakly supervised cropping methods (without bounding\nbox supervision) rely on the sliding window mechanism. The sliding window\nmechanism requires fixed aspect ratios and limits the cropping region with\narbitrary size. Moreover, the sliding window method usually produces tens of\nthousands of windows on the input image which is very time-consuming. Motivated\nby these challenges, we firstly formulate the aesthetic image cropping as a\nsequential decision-making process and propose a weakly supervised Aesthetics\nAware Reinforcement Learning (A2-RL) framework to address this problem.\nParticularly, the proposed method develops an aesthetics aware reward function\nwhich especially benefits image cropping. Similar to human's decision making,\nwe use a comprehensive state representation including both the current\nobservation and the historical experience. We train the agent using the\nactor-critic architecture in an end-to-end manner. The agent is evaluated on\nseveral popular unseen cropping datasets. Experiment results show that our\nmethod achieves the state-of-the-art performance with much fewer candidate\nwindows and much less time compared with previous weakly supervised methods.","url_abs":"http://arxiv.org/abs/1709.04595v3","url_pdf":"http://arxiv.org/pdf/1709.04595v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a2-rl-aesthetics-aware-reinforcement-learning","repo_url":"https://github.com/wuhuikai/TF-A2RL","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"a2-rl-aesthetics-aware-reinforcement-learning","repo_url":"https://github.com/pjhool/TF-A2RL-Test","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"a2-rl-aesthetics-aware-reinforcement-learning","repo_url":"https://github.com/sunyasheng/a2rl_pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"image-cropping","task_name":"Image Cropping"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"sequential-decision-making","task_name":"Sequential Decision Making"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"wuhuikai/TF-A2RL","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"pjhool/TF-A2RL-Test","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"sunyasheng/a2rl_pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"79542e0989d011fdcc9a8063f6415d2b38de396ef52da2e82cb3a1b97194e757","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}